Cross-domain Pedestrian Re-recognition Research by Fusing Pedestrian Detection Algorithms
Pages 383 - 388
Abstract
Pedestrian re-identification is a computer vision technique designed to identify the same pedestrian under different cameras, which is of great significance in fields such as public safety and intelligent transportation. In this paper, a pedestrian re-recognition model incorporating YOLOv7 target detection and pedestrian re-recognition algorithm is proposed. Firstly, a small target detection layer is added to the YOLOv7 detection algorithm, and a coordinate attention mechanism is added to the backbone network to improve the pedestrian detection capability. Cross-camera retrieval suffers from cross-domain problem, in this paper, by adding IBN-b module to the pedestrian re-recognition network, adding label smoothing strategy and removing random erasure during training, and using multiple datasets for co-training, and then verifying on Duke dataset, Rank-1 reaches 70.8% and mAP reaches 54.8%, which can meet the requirements of real scene applications.
References
[1]
X. L. Qian, Y. W. Fu, Y. G. Jiang, Multi-scale Deep Learning Architectures for Person Re-identification[C]. IEEE International Conference on Computer Vision. 2017: 5409-5418.
[2]
Y. F. Sun, L. Zheng, Y. Yang, Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)[C]. Lecture Notes in Computer Science. 2018: 501-518.
[3]
X. L. Qian, Y. W. Fu, T. Xiang, Pose-Normalized Image Generation for Person Re-identification[C]. Lecture Notes in Computer Science. 2018: 661-678.
[4]
C. Liu, X. J. Chang, Y. D. Shen, Unity Style Transfer for Person Re-Identification[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2020: 6886-6895.
[5]
R. Girshick, J. Donahue, T. Darrell, Rich feature hierarchies for accurate object detection and semantic segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2014: 580-587.
[6]
J. Redmon, S. Divvala, R. Girshick, You Only Look Once: Unified, Real-Time Object Detection[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2016: 779-788.
[7]
Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. Arxiv, 2022,
[8]
J. Hu, L. Shen, S. Albanie, Squeeze-and-Excitation Networks[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
[9]
Jongchan Park, Sanghyun Woo, Joon-Young Lee, BAM: Bottleneck Attention Module[J]. Arxiv, 2018,
[10]
Q. B. Hou, D. Q. Zhou, J. S. Feng, Coordinate Attention for Efficient Mobile Network Design[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2021: 13708-13717.
[11]
K. M. He, X. Y. Zhang, S. Q. Ren, Deep Residual Learning for Image Recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2016: 770-778.
[12]
Z. Zhong, L. Zheng, G. L. Kang, Random Erasing Data Augmentation[C]. AAAI Conference on Artificial Intelligence. 2020: 13001-13008.
[13]
X. G. Pan, P. Luo, J. P. Shi, Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net[C]. Lecture Notes in Computer Science. 2018: 484-500.
[14]
C. Szegedy, V. Vanhoucke, S. Ioffe, Rethinking the Inception Architecture for Computer Vision[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2016: 2818-2826.
Recommendations
Real-time pedestrian detection via hierarchical convolutional feature
With the development of pedestrian detection technologies, existing methods can not simultaneously satisfy high quality detection and fast calculation for practical applications. Therefore, the goal of our research is to balance of pedestrian detection ...
Robust pedestrian detection via constructing versatile pedestrian knowledge bank
AbstractPedestrian detection is a crucial field of computer vision research which can be adopted in various real-world applications (e.g., self-driving systems). However, despite noticeable evolution of pedestrian detection, pedestrian representations ...
Highlights- We propose to obtain versatile pedestrian representations for pedestrian detection.
- We exploit generalized pedestrian knowledge of a large-scale pretrained model.
- We build versatile pedestrian knowledge bank and leverage it in ...
Multi-spectral pedestrian detection
Pedestrian detection is a crucial problem in human pose recovery and behavior analysis, especially in applications such as visual surveillance, robotics, and drive-assistance systems. Recently, most pedestrian detection approaches of machine learning ...
Comments
Information & Contributors
Information
Published In
December 2023
1132 pages
ISBN:9798400716157
DOI:10.1145/3660043
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 May 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICIEAI 2023
ICIEAI 2023: 2023 International Conference on Information Education and Artificial Intelligence
December 22 - 24, 2023
Xiamen, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 8Total Downloads
- Downloads (Last 12 months)8
- Downloads (Last 6 weeks)3
Reflects downloads up to 05 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format